© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3116
    Prev
    Next
    INDEX
    Explanations

    sentences related to hardship and recovery of a person

    oai_token-act-pair · gemini-2.0-flash

    buy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.98
    fjspx
    -0.86
    NOPQRST
    -0.78
    UnusedPrivate
    -0.77
    
    -0.76
    Geplaatst
    -0.76
    InitVars
    -0.75
     ostavi
    -0.75
    ########.
    -0.72
    Personendaten
    -0.72
    POSITIVE LOGITS
     azért
    0.43
     Kim
    0.41
    Essentially
    0.40
    baiki
    0.39
    chanical
    0.38
    Natürlich
    0.38
    aarrggbb
    0.38
    Further
    0.37
    arova
    0.36
    By
    0.36
    Activations Density 2.992%

    No Known Activations